Python Coding challenge - Day 789| What is the output of the following Python Code?

 

Code Explanation:

Import PyTorch Library

import torch

import torch.nn as nn

Explanation:

torch is the main PyTorch package — it provides tensors, math operations, and autograd.

torch.nn (imported as nn) is the Neural Network module — it includes layers, activations, loss functions, etc.

We import it separately for convenience when defining neural network layers.

Define a Simple Neural Network Model

model = nn.Sequential(nn.Linear(4, 2), nn.ReLU())

Explanation:

nn.Sequential() creates a container that stacks layers in order.

Inside, two components are defined:

nn.Linear(4, 2) — a fully connected (dense) layer with:

4 input features

2 output features

It performs a linear transformation:

nn.ReLU() — a Rectified Linear Unit activation function, which replaces all negative values with zero.

So this model performs:

Linear mapping → Activation (ReLU).

Create Input Tensor

x = torch.ones(1, 4)

Explanation:

torch.ones(1, 4) creates a tensor of shape (1, 4) filled with 1s.

This represents one sample (batch size = 1) with 4 input features.

Example of the tensor:

tensor([[1., 1., 1., 1.]])

Forward Pass Through the Model

print(model(x).shape)

Explanation:

model(x) performs a forward pass:

Input x (size [1, 4]) is passed through nn.Linear(4, 2) → output size [1, 2].

Then nn.ReLU() is applied → keeps the same shape [1, 2], but clamps negatives to zero.

Finally, .shape prints the size of the output tensor.

Output

torch.Size([1, 2])

500 Days Python Coding Challenges with Explanation